INDEX

Explanations

descriptions indicating the action of treating someone or something

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.48

//

-0.78

var

-0.77

public

-0.75

AutoScaleMode

-0.75

Пор

-0.75

beta

-0.74

namespace

-0.72

import

-0.72

dom

-0.72

POSITIVE LOGITS

 maneu

2.38

Juf

2.35

fta

2.32

 increa

2.26

ftu

2.26

 thut

2.25

aen

2.24

 stockholm

2.23

 affor

2.19

 accla

2.17

Activations Density 0.114%

descriptions indicating the action of treating someone or something

No Comments

No Known Activations